mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 11:10:20 +01:00
74db141d5e
* SAC algorithm * SAC - updates to agent (learn_from_batch), sac_head and sac_q_head to fix problem in gradient calculation. Now SAC agents is able to train. gym_environment - fixing an error in access to gym.spaces * Soft Actor Critic - code cleanup * code cleanup * V-head initialization fix * SAC benchmarks * SAC Documentation * typo fix * documentation fixes * documentation and version update * README typo
Clipped PPO
Each experiment uses 3 seeds and is trained for 10M environment steps. The parameters used for Clipped PPO are the same parameters as described in the original paper.
Inverted Pendulum Clipped PPO - single worker
coach -p Mujoco_ClippedPPO -lvl inverted_pendulum
Inverted Double Pendulum Clipped PPO - single worker
coach -p Mujoco_ClippedPPO -lvl inverted_double_pendulum
Reacher Clipped PPO - single worker
coach -p Mujoco_ClippedPPO -lvl reacher
Hopper Clipped PPO - single worker
coach -p Mujoco_ClippedPPO -lvl hopper
Half Cheetah Clipped PPO - single worker
coach -p Mujoco_ClippedPPO -lvl half_cheetah
Walker 2D Clipped PPO - single worker
coach -p Mujoco_ClippedPPO -lvl walker2d
Ant Clipped PPO - single worker
coach -p Mujoco_ClippedPPO -lvl ant
Swimmer Clipped PPO - single worker
coach -p Mujoco_ClippedPPO -lvl swimmer
Humanoid Clipped PPO - single worker
coach -p Mujoco_ClippedPPO -lvl humanoid
