YunjiaXi / Implementation-and-Some-Modification-about-DQN-and-SAC
In this project, I explore some typical value-based and policy-based RL algorithms. I do experiments on DQN and its six variants and their combination in Atari environments Pong and Boxing. I also do some experiments on SAC with DDPG as baseline on three MuJoCo environments Hopper-v2, Ant-v2, and HalfCheetah-v2.
☆11Updated 4 years ago
Alternatives and similar repositories for Implementation-and-Some-Modification-about-DQN-and-SAC:
Users that are interested in Implementation-and-Some-Modification-about-DQN-and-SAC are comparing it to the libraries listed below
- Implement PPO algorithm on mujoco environment，such as Ant-v2, Humanoid-v2, Hopper-v2, Halfcheeth-v2.☆51Updated 4 years ago
- Implement DQN and DDQN algorithm on Atari games，such as BreakoutNoFrameskip-v4, PongNoFrameskip-v4,BoxingNoFrameskip-v4.☆15Updated 4 years ago
- Play Atari(Breakout) Game by DRL - DQN, Noisy DQN and A3C☆13Updated 4 years ago
- Paper list for constrained policy optimization in reinforcement learning.☆71Updated last year
- 强化学习 面试（未完待续）☆35Updated 5 years ago
- ILSwiss is an Easy-to-run Imitation Learning (IL, or Learning from Demonstration, LfD) and also Reinforcement Learning (RL) framework (te…☆166Updated last year
- PPO, DDPG, SAC implementation on mujoco environment☆106Updated 3 years ago
- A clean and robust Pytorch implementation of SAC on discrete action space☆35Updated 6 months ago
- Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (ICLR 2021, https://arxiv.org/abs/2010.01523). RODE is …☆74Updated 4 months ago
- Deep recurrent Q learning on CartPole-v1 environment☆89Updated last year
- Implementation of HIRO (Data-Efficient Hierarchical Reinforcement Learning)☆106Updated 3 years ago
- RL algorithms☆141Updated 4 years ago
- ☆75Updated 5 years ago
- Codes accompanying the paper "Learning Nearly Decomposable Value Functions with Communication Minimization" (ICLR 2020)☆81Updated 2 years ago
- ☆128Updated 9 months ago
- Basic reinforcement learning algorithms. Including:DQN,Double DQN, Dueling DQN, SARSA, REINFORCE, baseline-REINFORCE, Actor-Critic,DDPG,D…☆92Updated 4 years ago
- ☆52Updated 6 years ago
- Implementation of benchmark RL algorithms☆466Updated 2 years ago
- ☆93Updated 4 years ago
- Implement many Sparse Reward algorithms in Gym Fetch environment☆86Updated 4 years ago
- This is the official implementation of Multi-Agent PPO.☆104Updated 2 years ago
- ☆31Updated last year
- A clean and robust Pytorch implementation of PPO on continuous action space.☆143Updated 10 months ago
- The code for maddpg using pytorch☆168Updated 4 years ago
- Constrained Policy Optimization implementation on Safety Gym☆25Updated 3 years ago
- Implementation of the paper Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation - https:/…☆82Updated 7 years ago
- DQN to play Atari Pong☆114Updated 6 years ago
- ☆123Updated 3 years ago
- BranchingDQN☆49Updated 6 years ago
- [NeurIPS 2021] CDS achieves remarkable success in challenging benchmarks SMAC and GRF by balancing sharing and diversity.☆85Updated 2 years ago