{"id":20475366,"url":"https://github.com/ashwinpn/reinforcement-learning","last_synced_at":"2026-04-24T12:05:31.869Z","repository":{"id":201600117,"uuid":"245919009","full_name":"ashwinpn/Reinforcement-Learning","owner":"ashwinpn","description":"Research and implementations of Deep Learning / Reinforcement Learning agents and their implementations / applications","archived":false,"fork":false,"pushed_at":"2020-05-23T09:43:56.000Z","size":1827,"stargazers_count":2,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-05-29T13:11:50.809Z","etag":null,"topics":["deep-learning","deep-learning-framework","deep-neural-networks","deep-reinforcement-learning","machine-learning","machine-learning-algorithms","machinelearning","reinforcement","reinforcement-learning","reinforcement-learning-agent","reinforcement-learning-algorithms","reinforcement-learning-environments","rl"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ashwinpn.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2020-03-09T01:35:54.000Z","updated_at":"2020-09-22T13:25:23.000Z","dependencies_parsed_at":null,"dependency_job_id":"700c122d-1a84-44d5-8e1a-4df17fdac75d","html_url":"https://github.com/ashwinpn/Reinforcement-Learning","commit_stats":null,"previous_names":["ashwinpn/reinforcement-learning"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ashwinpn/Reinforcement-Learning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ashwinpn%2FReinforcement-Learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ashwinpn%2FReinforcement-Learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ashwinpn%2FReinforcement-Learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ashwinpn%2FReinforcement-Learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ashwinpn","download_url":"https://codeload.github.com/ashwinpn/Reinforcement-Learning/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ashwinpn%2FReinforcement-Learning/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261514318,"owners_count":23170355,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","deep-learning-framework","deep-neural-networks","deep-reinforcement-learning","machine-learning","machine-learning-algorithms","machinelearning","reinforcement","reinforcement-learning","reinforcement-learning-agent","reinforcement-learning-algorithms","reinforcement-learning-environments","rl"],"created_at":"2024-11-15T15:15:49.036Z","updated_at":"2026-04-24T12:05:26.834Z","avatar_url":"https://github.com/ashwinpn.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n----------\n\n##### Contents\n\n- [RL Landscape](#rl-landscape)\n- [RL History](#rl-history)\n- [RL Agents Implementation](#rl-agents-implementation)\n  - [Value Optimization Agents](#value-optimization-agents)\n  - [Policy Optimization Agents](#policy-optimization-agents)\n  - [General Agents](#general-agents)\n  - [Imitation Learning Agents](#imitation-learning-agents)\n  - [Hierarchical Reinforcement Learning Agents](#hierarchical-reinforcement-learning-agents)\n  - [Memory Types](#memory-types)\n  - [Exploration Techniques](#exploration-techniques)\n- [RL Environments](#rl-environments)\n- [RL Mechanisms](#rl-mechanisms)\n- [RL Applications](#)\n  - [RL Games](#rl-games)\n  - [DRL applied to Robotics](#drl-applied-to-robotics)\n  - [DRL applied to NLP](#drl-applied-to-nlp)\n  - [DRL applied to Vision](#drl-applied-to-vision)\n- [References](#references)\n  - Reference Implementations\n  - Review Papers\n  - RL Platforms\n  - Deep Reinforcement Learning Papers\n\n[Back to top](#contents)\n\n\n\n----------------\n\n![deep_rl](https://github.com/gopala-kr/DRL-Agents/blob/master/resources/img/drl.PNG)\n\n------------\n#### RL Landscape\n\n[Back to top](#contents)\n\n![68747470733a2f2f706c616e73706163652e6f72672f32303137303833302d6265726b656c65795f646565705f726c5f626f6f7463616d702f696d672f616e6e6f74617465642e6a7067](https://camo.githubusercontent.com/9f59450ab0458e82c4d728415a4d0f1671ea8a48/68747470733a2f2f706c616e73706163652e6f72672f32303137303833302d6265726b656c65795f646565705f726c5f626f6f7463616d702f696d672f616e6e6f74617465642e6a7067)\n\n--------------\n\n![reinforcement-learning](https://github.com/eleurent/phd-bibliography/blob/master/reinforcement-learning.svg)\n\n\nSource:  [eleurent/phd-bibliography](https://github.com/eleurent/phd-bibliography)\n\n--------------\n\n#### RL Agents Implementation\n\n[Back to top](#contents)\n\n\n![algorithms](https://github.com/NervanaSystems/coach/blob/master/img/algorithms.png)\n\n   - Value Optimization\n       - [QR-DQN]\n       - [DQN] - [[Slides](https://drive.google.com/file/d/0BxXI_RttTZAhVUhpbDhiSUFFNjg/view)]  [[Code](https://github.com/deepmind/dqn)] [[rainbow](https://github.com/hengyuan-hu/rainbow)]\n       - [Bootstrapped DQN]\n       - [DDQN]\n       - [NEC]\n       - [MMC]\n       - [N-step Q Learning]\n       - [PAL]\n       - [Categorical DQN]\n       - [NAF]\n   - Policy Optimization\n       - [Policy Gradient]\n       - [Actor Critic]\n         - [DDPG] [[Code](https://github.com/ghliu/pytorch-ddpg)]\n           - [HAC DDPG]\n           - [DDPG with HER]\n         - [Clipped PPO]\n         - [PPO]\n   - [DFP]\n   - Imitation\n       - [Behavioural cloning]\n       - [Inverse Reinforcement Learning] [[Code](https://github.com/MatthewJA/Inverse-Reinforcement-Learning)] [[irl-imitation-code](https://github.com/yrlu/irl-imitation)]\n       - [Generative Adversarial Imitation Learning]\n       \n-----------\n\n##### Value Optimization Agents\n\n[Back to top](#contents)\n\n* [Deep Q Network (DQN)](https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf)  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/dqn_agent.py))\n* [Double Deep Q Network (DDQN)](https://arxiv.org/pdf/1509.06461.pdf)  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/ddqn_agent.py))\n* [Dueling Q Network](https://arxiv.org/abs/1511.06581)\n* [Mixed Monte Carlo (MMC)](https://arxiv.org/abs/1703.01310)  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/mmc_agent.py))\n* [Persistent Advantage Learning (PAL)](https://arxiv.org/abs/1512.04860)  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/pal_agent.py))\n* [Categorical Deep Q Network (C51)](https://arxiv.org/abs/1707.06887)  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/categorical_dqn_agent.py))\n* [Quantile Regression Deep Q Network (QR-DQN)](https://arxiv.org/pdf/1710.10044v1.pdf)  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/qr_dqn_agent.py))\n* [N-Step Q Learning](https://arxiv.org/abs/1602.01783) | **Distributed**  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/n_step_q_agent.py))\n* [Neural Episodic Control (NEC)](https://arxiv.org/abs/1703.01988)  ([code](rl_coach/agents/nec_agent.py))\n* [Normalized Advantage Functions (NAF)](https://arxiv.org/abs/1603.00748.pdf) | **Distributed**  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/naf_agent.py))\n\n\n##### Policy Optimization Agents\n\n[Back to top](#contents)\n\n\n* [Policy Gradients (PG)](http://www-anw.cs.umass.edu/~barto/courses/cs687/williams92simple.pdf) | **Distributed**  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/policy_gradients_agent.py))\n* [Asynchronous Advantage Actor-Critic (A3C)](https://arxiv.org/abs/1602.01783) | **Distributed**  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/actor_critic_agent.py))\n* [Deep Deterministic Policy Gradients (DDPG)](https://arxiv.org/abs/1509.02971) | **Distributed**  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/ddpg_agent.py))\n* [Proximal Policy Optimization (PPO)](https://arxiv.org/pdf/1707.06347.pdf)  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/ppo_agent.py))\n* [Clipped Proximal Policy Optimization (CPPO)](https://arxiv.org/pdf/1707.06347.pdf) | **Distributed**  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/clipped_ppo_agent.py))\n* [Generalized Advantage Estimation (GAE)](https://arxiv.org/abs/1506.02438) ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/actor_critic_agent.py#L86))\n\n##### General Agents\n\n[Back to top](#contents)\n\n* [Direct Future Prediction (DFP)](https://arxiv.org/abs/1611.01779) | **Distributed**  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/dfp_agent.py))\n\n##### Imitation Learning Agents\n\n[Back to top](#contents)\n\n* Behavioral Cloning (BC)  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/bc_agent.py))\n\n##### Hierarchical Reinforcement Learning Agents\n\n[Back to top](#contents)\n\n* [Hierarchical Actor Critic (HAC)](https://arxiv.org/abs/1712.00948.pdf) ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/ddpg_hac_agent.py))\n\n##### Memory Types\n\n[Back to top](#contents)\n\n* [Hindsight Experience Replay (HER)](https://arxiv.org/abs/1707.01495.pdf) ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/memories/episodic/episodic_hindsight_experience_replay.py))\n* [Prioritized Experience Replay (PER)](https://arxiv.org/abs/1511.05952) ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/memories/non_episodic/prioritized_experience_replay.py))\n\n##### Exploration Techniques\n\n[Back to top](#contents)\n\n* E-Greedy ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/exploration_policies/e_greedy.py))\n* Boltzmann ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/exploration_policies/boltzmann.py))\n* Ornstein–Uhlenbeck process ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/exploration_policies/ou_process.py))\n* Normal Noise ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/exploration_policies/additive_noise.py))\n* Truncated Normal Noise ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/exploration_policies/truncated_normal.py))\n* [Bootstrapped Deep Q Network](https://arxiv.org/abs/1602.04621)  ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/agents/bootstrapped_dqn_agent.py))\n* [UCB Exploration via Q-Ensembles (UCB)](https://arxiv.org/abs/1706.01502) ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/exploration_policies/ucb.py))\n* [Noisy Networks for Exploration](https://arxiv.org/abs/1706.10295) ([code](https://github.com/NervanaSystems/coach/blob/master/rl_coach/exploration_policies/parameter_noise.py))\n\n-------------\n\n#### RL History\n\n[Back to top](#contents)\n\n\n- Temporal difference(TD) learning (1988)\n- Q‐learning (1998)\n- BayesRL (2002)\n- RMAX (2002)\n- CBPI (2002)\n- PEGASUS (2002)\n- Least‐Squares Policy Iteration (2003)\n- Fitted Q‐Iteration (2005)\n- GTD (2009)\n- UCRL (2010)\n- REPS (2010)\n- DQN (2014) - DeepMind\n\n----------\n\n[Back to top](#contents)\n\n![awesome](https://raw.githubusercontent.com/tigerneil/awesome-deep-rl/master/images/awesome-drl.png)\n\n\n---------\n\n[Back to top](#contents)\n\n![landscape](https://raw.githubusercontent.com/tangzhenyu/Reinforcement-Learning-in-Robotics/master/images/landscape.jpeg)\n---------\n#### RL Environments\n\n[Back to top](#contents)\n\n- [Acrobot]\n- [Bike]\n- [Blackjack]\n- [Cartpole]\n- [ContextBandit]\n- [Continuous Chain]\n- [Corridor]\n- [Discrete Chain]\n- [Discretiser (for continuous environments)]\n- [Double Loop]\n- [Environment]\n- [Gridworld]\n- [Inventory management]\n- [Linear context bandit]\n- [Linear dynamic quadratic]\n- [Mountaincar (2d and 3d)]\n- [POMDP Maze]\n- [Optimistic Task]\n- [Puddleworld]\n- [Random MDPs]\n- [Riverswim]\n\n----------\n\n#### RL Mechanisms\n\n[Back to top](#contents)\n\n\n- [Attention and Memory]\n- [Unsupervised learning ]\n  - [GANs]\n  - [GQN]\n  - [UNREAL]\n- [Hierarchical RL]\n  - [FuNs]\n  - [Option-Critic]\n  - [STRAW]\n  - [h-DQN]\n  - [Stochastic Neural Networks]\n- [Multi-agent RL]\n- [Relational RL]\n- [Learning to Learn, a.k.a. Meta-Learning]\n  - [Few/One/Zero-shot Learning]\n    - [MAML]\n  - [Transfer and Multi-Task Learning]\n  - [Learning to Optimize]\n  - [Learning to Re-inforcement Learn]\n  - [Learning Combinatorial Optimization]\n  - [AutoML]\n  \n-------------------\n\n#### RL Games\n\n[Back to top](#contents)\n\n\n- Chinook (1997;2007) for Checkers,\n- Deep Blue (2002) for chess,\n- Logistello (1999) for Othello,\n- TD-Gammon (1994) for Backgammon,\n- GIB (2001) for contract bridge,\n- MoHex (2017) for Hex,\n- DQN (2016)(2018) for Atari 2600 games,\n- AlphaGo (2016a) and AlphaGo Zero (2017) for Go,\n- Alpha Zero (2017) for chess, shogi, and Go,\n- Cepheus (2015), DeepStack (2017), and Libratus (2017a;b) for heads-up Texas Hold’em Poker,\n- Jaderberg et al. (2018) for Quake III Arena Capture the Flag,\n- OpenAI Five, for Dota 2 at 5v5, https://openai.com/five/,\n- Zambaldi et al. (2018), Sun et al. (2018), and Pang et al. (2018) for StarCraft II\n\n-----------------\n\n\n[Back to top](#contents)\n\n- [Board Games]\n  - [Computer Go]\n  - [AlphaGo: Trainig pipeline with MCTS]\n  - [AlphaGo Zero]\n  - [Alpha Zero]\n- [Card Games]\n  - [DeepStack]\n- [Video Games]\n  - [Atari 2600 games]\n  - [StarCraft]\n  - [StarCraft\nII mini-games]\n  - [Quake III Arena]\n  - [Minecraft]\n  - [Super Smash Bros]\n  - [Doom]\n  - [ViZDoom]\n  \n------------\n\n#### DRL applied to Robotics\n\n[Back to top](#contents)\n\n\n   - [Sim-to-Real]\n     - [MuJoCo]\n   - [Imitation Learning]\n   - [Value-based Learning]\n   - [Policy-based Learning]\n   - [Model-based Learning]\n   - [Autonomous Driving Vehicles]\n\n-------------\n\n#### DRL applied to NLP\n\n[Back to top](#contents)\n\n- [Sequence Generation]\n- [Machine Translation]\n- [Dialogue Systems]\n\n------------\n\n#### DRL applied to Vision\n\n[Back to top](#contents)\n\n- [Recognition]\n- [Motion Analysis]\n- [Scene Understanding]\n- [Vision + NLP]\n- [Visual Control]\n- [Interactive Perception]\n\n\n----------------\n\n#### References\n\n[Back to top](#contents)\n\n\n- [reference implementations](https://github.com/gopala-kr/reinforce-tf/blob/master/ref-implementations.md)\n- [review papers](https://github.com/gopala-kr/reinforce-tf/blob/master/review-papers.md)\n- [RL platforms](https://github.com/gopala-kr/DRL-Agents/blob/master/platforms.md)\n- [deep-reinforcement-learning-papers](https://github.com/junhyukoh/deep-reinforcement-learning-papers)\n- [ICLR2019-RL-Papers](https://github.com/ewanlee/ICLR2019-RL-Papers)\n\n-------------\n- [deepmind.com/blog](https://deepmind.com/blog/)\n- [blog.openai](https://blog.openai.com/)\n- [openai/spinningup](https://github.com/openai/spinningup)\n- [DeepRLHacks](https://github.com/williamFalcon/DeepRLHacks)-Deep RL Bootcamp (Aug 2017)\n- [Deep RL Bootcamp](https://sites.google.com/view/deep-rl-bootcamp/lectures)\n- [UC Berkeley: Deep Reinforcement Learning](http://rail.eecs.berkeley.edu/deeprlcourse/)\n- [MIT 6.S094: Deep Learning for Self-Driving Cars](https://selfdrivingcars.mit.edu/)\n- [Deep Reinforcement Learning and Control \nSpring 2017, CMU 10703](https://katefvision.github.io/#readings)\n- [Sutton \u0026 Barto's: Reinforcement Learning: An Introduction](https://github.com/ShangtongZhang/reinforcement-learning-an-introduction)\n- [Algorithms for Reinforcement Learning](https://sites.ualberta.ca/~szepesva/papers/RLAlgsInMDPs.pdf)\n- [reinforcejs](https://cs.stanford.edu/people/karpathy/reinforcejs/index.html)\n- [Hands-On-Reinforcement-Learning-With-Python](https://github.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python)\n- [jetson-reinforcement](https://github.com/dusty-nv/jetson-reinforcement)\n- [DEEP REINFORCEMENT LEARNING](https://arxiv.org/pdf/1810.06339v1.pdf)\n- [Reinforcement Learning Applications](https://medium.com/@yuxili/rl-applications-73ef685c07eb)\n- [Lessons Learned Reproducing a Deep Reinforcement Learning Paper](http://amid.fish/reproducing-deep-rl)\n- [Scalable Deep Reinforcement Learning for Robotic Manipulation](https://ai.googleblog.com/2018/06/scalable-deep-reinforcement-learning.html)\n- [Closing the Simulation-to-Reality Gap for Deep Robotic Learning](https://ai.googleblog.com/2017/10/closing-simulation-to-reality-gap-for.html)\n- [Intel AI : demystifying-deep-reinforcement-learning](https://ai.intel.com/demystifying-deep-reinforcement-learning/)\n- [Intel AI : deep-reinforcement-learning-with-neon](https://ai.intel.com/deep-reinforcement-learning-with-neon/)\n- [Intel AI : reinforcement-learning-coach-intel](https://ai.intel.com/reinforcement-learning-coach-intel/)\n- [eecs.berkeley.deeprlcourse](http://rail.eecs.berkeley.edu/deeprlcourse/)\n- [Deep Learning for Video Game Playing](https://arxiv.org/pdf/1708.07902.pdf)\n- [Deep Reinforcement Learning that Matters](https://arxiv.org/pdf/1709.06560.pdf)\n- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://arxiv.org/pdf/1712.07107.pdf)\n- [Reinforcement learning](https://yandexdataschool.com/edu-process/rl)\n- [A Survey of Inverse Reinforcement Learning:\nChallenges, Methods and Progress\n](https://arxiv.org/pdf/1806.06877v1.pdf)\n- [A Survey of Knowledge Representation and Retrieval\nfor Learning in Service Robotics](https://arxiv.org/pdf/1807.02192v1.pdf)\n- [Applications of Deep Reinforcement Learning in\nCommunications and Networking: A Survey](https://arxiv.org/pdf/1810.07862v1.pdf)\n- [An Introduction to Deep Reinforcement Learning](https://arxiv.org/abs/1811.12560v2)\n- [Challenges of Real-World Reinforcement Learning](https://arxiv.org/abs/1904.12901v1)\n- [Modern Deep Reinforcement Learning Algorithms](https://arxiv.org/abs/1906.10025v1)\n\n----------------------------------------\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fashwinpn%2Freinforcement-learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fashwinpn%2Freinforcement-learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fashwinpn%2Freinforcement-learning/lists"}